English
Related papers

Related papers: Cluster-based Input Weight Initialization for Echo…

200 papers

Recurrent spiking neural networks (RSNNs) hold great potential for advancing artificial general intelligence, as they draw inspiration from the biological nervous system and show promise in modeling complex dynamics. However, the…

Neural and Evolutionary Computing · Computer Science 2023-05-30 Guan Wang , Yuhao Sun , Sijie Cheng , Sen Song

Deep convolutional neural networks are known to be unstable during training at high learning rate unless normalization techniques are employed. Normalizing weights or activations allows the use of higher learning rates, resulting in faster…

Machine Learning · Computer Science 2019-12-02 Brendan Ruff , Taylor Beck , Joscha Bach

A proper initialization of the weights in a neural network is critical to its convergence. Current insights into weight initialization come primarily from linear activation functions. In this paper, I develop a theory for weight…

Machine Learning · Computer Science 2017-05-04 Siddharth Krishna Kumar

Spatio-temporal area-level datasets play a critical role in official statistics, providing valuable insights for policy-making and regional planning. Accurate modeling and forecasting of these datasets can be extremely useful for…

Machine Learning · Computer Science 2026-01-06 Zhenhua Wang , Scott H. Holan , Christopher K. Wikle

In recurrent neural networks (RNNs) used to model biological neural networks, noise is typically introduced during training to emulate biological variability and regularize learning. The expectation is that removing the noise at test time…

Neural and Evolutionary Computing · Computer Science 2026-01-09 Noah Eckstein , Manoj Srinivasan

Spiking neural networks (SNNs) underlie low-power, fault-tolerant information processing in the brain and could constitute a power-efficient alternative to conventional deep neural networks when implemented on suitable neuromorphic hardware…

Neural and Evolutionary Computing · Computer Science 2022-10-13 Julian Rossbroich , Julia Gygax , Friedemann Zenke

We study the uniform approximation of echo state networks with randomly generated internal weights. These models, in which only the readout weights are optimized during training, have made empirical success in learning dynamical systems.…

Machine Learning · Computer Science 2024-06-05 Zhen Li , Yunfei Yang

This paper is concerned with the sparsification of the input-hidden weights of ELM (Extreme Learning Machine). For ordinary feedforward neural networks, the sparsification is usually done by introducing certain regularization technique into…

Machine Learning · Computer Science 2018-01-23 Feng Li , Sibo Yang , Huanhuan Huang , Wei Wu

Recurrent stochastic configuration networks (RSCNs) are a class of randomized learner models that have shown promise in modelling nonlinear dynamics. In many fields, however, the data generated by industry systems often exhibits…

Machine Learning · Computer Science 2024-10-15 Gang Dang , Dianhui Wang

In this study, an efficient stochastic gradient-free method, the ensemble neural networks (ENN), is developed. In the ENN, the optimization process relies on covariance matrices rather than derivatives. The covariance matrices are…

Machine Learning · Statistics 2019-11-11 Yuntian Chen , Haibin Chang , Meng Jin , Dongxiao Zhang

To model time-varying nonlinear temporal dynamics in sequential data, a recurrent network capable of varying and adjusting the recurrence depth between input intervals is examined. The recurrence depth is extended by several intermediate…

Machine Learning · Computer Science 2017-08-15 Hyunsin Park , Chang D. Yoo

There is an implicit assumption that by unfolding recurrent neural networks (RNN) in finite time, the misspecification of choosing a zero value for the initial hidden state is mitigated by later time steps. This assumption has been shown to…

Machine Learning · Computer Science 2019-02-12 Sam Wenke , Jim Fleming

Continual Learning (CL) refers to a learning setup where data is non stationary and the model has to learn without forgetting existing knowledge. The study of CL for sequential patterns revolves around trained recurrent networks. In this…

Machine Learning · Computer Science 2021-08-18 Andrea Cossu , Davide Bacciu , Antonio Carta , Claudio Gallicchio , Vincenzo Lomonaco

The prefrontal cortex is known to be involved in many high-level cognitive functions, in particular, working memory. Here, we study to what extent a group of randomly connected units (namely an Echo State Network, ESN) can store and…

Neurons and Cognition · Quantitative Biology 2018-06-19 Anthony Strock , Nicolas Rougier , Xavier Hinaut

The ability to learn and retain a wide variety of tasks is a hallmark of human intelligence that has inspired research in artificial general intelligence. Continual learning approaches provide a significant step towards achieving this goal.…

Machine Learning · Computer Science 2025-06-04 Shriraj P. Sawant , Krishna P. Miyapuram

We propose an experimental comparison between Deep Echo State Networks (DeepESNs) and gated Recurrent Neural Networks (RNNs) on multivariate time-series prediction tasks. In particular, we compare reservoir and fully-trained RNNs able to…

Machine Learning · Computer Science 2019-11-21 Claudio Gallicchio , Alessio Micheli , Luca Pedrelli

Convolutional Neural Networks spread through computer vision like a wildfire, impacting almost all visual tasks imaginable. Despite this, few researchers dare to train their models from scratch. Most work builds on one of a handful of…

Computer Vision and Pattern Recognition · Computer Science 2016-09-26 Philipp Krähenbühl , Carl Doersch , Jeff Donahue , Trevor Darrell

Using data from mobile network utilization in Norway, we showcase the possibility of monitoring the state of communication and mobility networks with a non-invasive, low-cost method. This method transforms the network data into a model…

Machine Learning · Computer Science 2025-09-01 Felix Simon Reimers , Carl-Hendrik Peters , Stefano Nichele

Deep neural networks achieve state-of-the-art performance for a range of classification and inference tasks. However, the use of stochastic gradient descent combined with the nonconvexity of the underlying optimization problems renders…

Machine Learning · Computer Science 2020-01-29 Ramina Ghods , Andrew S. Lan , Tom Goldstein , Christoph Studer

This work presents our ongoing research of unsupervised pretraining in neural machine translation (NMT). In our method, we initialize the weights of the encoder and decoder with two language models that are trained with monolingual data and…

Computation and Language · Computer Science 2020-10-20 Dušan Variš , Ondřej Bojar